Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, non-destructive and closed-world, but the description adds genuinely non-redundant detail: it requires existing OAuth docs:read consent, requests no new write grant, performs no network request or telemetry, and refuses invalid arguments. It also warns that 'central support availability is independent from this local descriptor,' clarifying that this is a static local document rather than a live check. Some of this is duplicated (two overlapping negative lists), which keeps it from a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded, which is good, but the closing four sentences are bloated and self-repeating: consent is stated twice in consecutive sentences, and the non-action list appears in two overlapping variants. Several clauses ('use the canonical endpoint with the central lookup tool when locating this listing') are opaque and do not earn their space.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With zero parameters, a real output schema, and full annotation coverage, the bar is low, and the description still covers auth requirements, side-effect absence, and the local-vs-central distinction. The only incompleteness is that the returned 'strict public-directory support descriptor' is described only in vague terms, though the output schema carries that burden.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes zero parameters and the schema coverage is 100%, so there is nothing for the description to disambiguate — baseline 4 applies. The line 'Invalid arguments are refused' is consistent with additionalProperties: false but adds little beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a specific verb and resource: 'Read the public MCP support workflow and privacy contract for the connected SuperCatch server.' That is concrete and distinguishable from data-mutation siblings. It never contrasts itself with the closest reads (supercatch_get_help_resource, supercatch_search_public_docs, supercatch_get_capabilities), so an agent must infer the boundary from the 'public-directory support descriptor' phrasing alone.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The 'Use to find ...' sentence gives a positive trigger, and the exclusion list ('does not submit an issue, record an outcome, read a private case, forward a credential, or subscribe a webhook') supplies when-not guidance. However, the named artifacts (central public-directory issue, receipt, reopen, owner, change-feed, voluntary outcome tools) do not correspond to any sibling tool names, so it does not route the agent to an actual alternative.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.